X-Git-Url: http://plrg.eecs.uci.edu/git/?p=oota-llvm.git;a=blobdiff_plain;f=include%2Fllvm%2FAnalysis%2FTargetTransformInfo.h;h=1a7f6f6cfc04fdb55a50f6929154e91a57346854;hp=e1331a16b3bc15ff4bc905cb37cb94b9d3550385;hb=5733100450b4935784b3d352160cfe6424cec226;hpb=fb55a8fd7c38aa09d9c243d48a8a72d890f36a3d diff --git a/include/llvm/Analysis/TargetTransformInfo.h b/include/llvm/Analysis/TargetTransformInfo.h index e1331a16b3b..1a7f6f6cfc0 100644 --- a/include/llvm/Analysis/TargetTransformInfo.h +++ b/include/llvm/Analysis/TargetTransformInfo.h @@ -1,4 +1,4 @@ -//===- llvm/Analysis/TargetTransformInfo.h ----------------------*- C++ -*-===// +//===- TargetTransformInfo.h ------------------------------------*- C++ -*-===// // // The LLVM Compiler Infrastructure // @@ -6,67 +6,89 @@ // License. See LICENSE.TXT for details. // //===----------------------------------------------------------------------===// -// -// This pass exposes codegen information to IR-level passes. Every -// transformation that uses codegen information is broken into three parts: -// 1. The IR-level analysis pass. -// 2. The IR-level transformation interface which provides the needed -// information. -// 3. Codegen-level implementation which uses target-specific hooks. -// -// This file defines #2, which is the interface that IR-level transformations -// use for querying the codegen. -// +/// \file +/// This pass exposes codegen information to IR-level passes. Every +/// transformation that uses codegen information is broken into three parts: +/// 1. The IR-level analysis pass. +/// 2. The IR-level transformation interface which provides the needed +/// information. +/// 3. Codegen-level implementation which uses target-specific hooks. +/// +/// This file defines #2, which is the interface that IR-level transformations +/// use for querying the codegen. +/// //===----------------------------------------------------------------------===// #ifndef LLVM_ANALYSIS_TARGETTRANSFORMINFO_H #define LLVM_ANALYSIS_TARGETTRANSFORMINFO_H -#include "llvm/CodeGen/ValueTypes.h" -#include "llvm/IR/GlobalValue.h" +#include "llvm/ADT/Optional.h" +#include "llvm/IR/IntrinsicInst.h" #include "llvm/IR/Intrinsics.h" -#include "llvm/IR/Type.h" #include "llvm/Pass.h" #include "llvm/Support/DataTypes.h" +#include namespace llvm { -/// TargetTransformInfo - This pass provides access to the codegen -/// interfaces that are needed for IR-level transformations. +class Function; +class GlobalValue; +class Loop; +class PreservedAnalyses; +class Type; +class User; +class Value; + +/// \brief Information about a load/store intrinsic defined by the target. +struct MemIntrinsicInfo { + MemIntrinsicInfo() + : ReadMem(false), WriteMem(false), Vol(false), MatchingId(0), + NumMemRefs(0), PtrVal(nullptr) {} + bool ReadMem; + bool WriteMem; + bool Vol; + // Same Id is set by the target for corresponding load/store intrinsics. + unsigned short MatchingId; + int NumMemRefs; + Value *PtrVal; +}; + +/// \brief This pass provides access to the codegen interfaces that are needed +/// for IR-level transformations. class TargetTransformInfo { -protected: - /// \brief The TTI instance one level down the stack. +public: + /// \brief Construct a TTI object using a type implementing the \c Concept + /// API below. /// - /// This is used to implement the default behavior all of the methods which - /// is to delegate up through the stack of TTIs until one can answer the - /// query. - TargetTransformInfo *PrevTTI; + /// This is used by targets to construct a TTI wrapping their target-specific + /// implementaion that encodes appropriate costs for their target. + template TargetTransformInfo(T Impl); - /// \brief The top of the stack of TTI analyses available. + /// \brief Construct a baseline TTI object using a minimal implementation of + /// the \c Concept API below. /// - /// This is a convenience routine maintained as TTI analyses become available - /// that complements the PrevTTI delegation chain. When one part of an - /// analysis pass wants to query another part of the analysis pass it can use - /// this to start back at the top of the stack. - TargetTransformInfo *TopTTI; - - /// All pass subclasses must in their initializePass routine call - /// pushTTIStack with themselves to update the pointers tracking the previous - /// TTI instance in the analysis group's stack, and the top of the analysis - /// group's stack. - void pushTTIStack(Pass *P); - - /// All pass subclasses must in their finalizePass routine call popTTIStack - /// to update the pointers tracking the previous TTI instance in the analysis - /// group's stack, and the top of the analysis group's stack. - void popTTIStack(); - - /// All pass subclasses must call TargetTransformInfo::getAnalysisUsage. - virtual void getAnalysisUsage(AnalysisUsage &AU) const; + /// The TTI implementation will reflect the information in the DataLayout + /// provided if non-null. + explicit TargetTransformInfo(const DataLayout *DL); -public: - /// This class is intended to be subclassed by real implementations. - virtual ~TargetTransformInfo() = 0; + // Provide move semantics. + TargetTransformInfo(TargetTransformInfo &&Arg); + TargetTransformInfo &operator=(TargetTransformInfo &&RHS); + + // We need to define the destructor out-of-line to define our sub-classes + // out-of-line. + ~TargetTransformInfo(); + + /// \brief Handle the invalidation of this information. + /// + /// When used as a result of \c TargetIRAnalysis this method will be called + /// when the function this was computed for changes. When it returns false, + /// the information is preserved across those changes. + bool invalidate(Function &, const PreservedAnalyses &) { + // FIXME: We should probably in some way ensure that the subtarget + // information for a function hasn't changed. + return false; + } /// \name Generic Target Information /// @{ @@ -77,7 +99,7 @@ public: /// fundamental values that should be used to interpret (and produce) those /// costs. The costs are returned as an unsigned rather than a member of this /// enumeration because it is expected that the cost of one IR instruction - /// may have a multiplicative factor to it or otherwise won't fit dircetly + /// may have a multiplicative factor to it or otherwise won't fit directly /// into the enum. Moreover, it is common to sum or average costs which works /// better as simple integral values. Thus this enum only provides constants. /// @@ -87,9 +109,9 @@ public: /// skipped by renaming the registers in the CPU, but they still are encoded /// and thus wouldn't be considered 'free' here. enum TargetCostConstants { - TCC_Free = 0, ///< Expected to fold away in lowering. - TCC_Basic = 1, ///< The cost of a typical 'add' instruction. - TCC_Expensive = 4 ///< The cost of a 'div' instruction on x86. + TCC_Free = 0, ///< Expected to fold away in lowering. + TCC_Basic = 1, ///< The cost of a typical 'add' instruction. + TCC_Expensive = 4 ///< The cost of a 'div' instruction on x86. }; /// \brief Estimate the cost of a specific operation when lowered. @@ -106,16 +128,15 @@ public: /// /// The returned cost is defined in terms of \c TargetCostConstants, see its /// comments for a detailed explanation of the cost values. - virtual unsigned getOperationCost(unsigned Opcode, Type *Ty, - Type *OpTy = 0) const; + unsigned getOperationCost(unsigned Opcode, Type *Ty, + Type *OpTy = nullptr) const; /// \brief Estimate the cost of a GEP operation when lowered. /// /// The contract for this function is the same as \c getOperationCost except /// that it supports an interface that provides extra information specific to /// the GEP operation. - virtual unsigned getGEPCost(const Value *Ptr, - ArrayRef Operands) const; + unsigned getGEPCost(const Value *Ptr, ArrayRef Operands) const; /// \brief Estimate the cost of a function call when lowered. /// @@ -126,31 +147,31 @@ public: /// This is the most basic query for estimating call cost: it only knows the /// function type and (potentially) the number of arguments at the call site. /// The latter is only interesting for varargs function types. - virtual unsigned getCallCost(FunctionType *FTy, int NumArgs = -1) const; + unsigned getCallCost(FunctionType *FTy, int NumArgs = -1) const; /// \brief Estimate the cost of calling a specific function when lowered. /// /// This overload adds the ability to reason about the particular function /// being called in the event it is a library call with special lowering. - virtual unsigned getCallCost(const Function *F, int NumArgs = -1) const; + unsigned getCallCost(const Function *F, int NumArgs = -1) const; /// \brief Estimate the cost of calling a specific function when lowered. /// /// This overload allows specifying a set of candidate argument values. - virtual unsigned getCallCost(const Function *F, - ArrayRef Arguments) const; + unsigned getCallCost(const Function *F, + ArrayRef Arguments) const; /// \brief Estimate the cost of an intrinsic when lowered. /// /// Mirrors the \c getCallCost method but uses an intrinsic identifier. - virtual unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy, - ArrayRef ParamTys) const; + unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy, + ArrayRef ParamTys) const; /// \brief Estimate the cost of an intrinsic when lowered. /// /// Mirrors the \c getCallCost method but uses an intrinsic identifier. - virtual unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy, - ArrayRef Arguments) const; + unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy, + ArrayRef Arguments) const; /// \brief Estimate the cost of a given IR user when lowered. /// @@ -167,7 +188,22 @@ public: /// /// The returned cost is defined in terms of \c TargetCostConstants, see its /// comments for a detailed explanation of the cost values. - virtual unsigned getUserCost(const User *U) const; + unsigned getUserCost(const User *U) const; + + /// \brief Return true if branch divergence exists. + /// + /// Branch divergence has a significantly negative impact on GPU performance + /// when threads in the same wavefront take different paths due to conditional + /// branches. + bool hasBranchDivergence() const; + + /// \brief Returns whether V is a source of divergence. + /// + /// This function provides the target-dependent information for + /// the target-independent DivergenceAnalysis. DivergenceAnalysis first + /// builds the dependency graph, and then runs the reachability algorithm + /// starting with the sources of divergence. + bool isSourceOfDivergence(const Value *V) const; /// \brief Test whether calls to a function lower to actual program function /// calls. @@ -179,9 +215,58 @@ public: /// should probably move to simpler cost metrics using the above. /// Alternatively, we could split the cost interface into distinct code-size /// and execution-speed costs. This would allow modelling the core of this - /// query more accurately as the a call is a single small instruction, but + /// query more accurately as a call is a single small instruction, but /// incurs significant execution cost. - virtual bool isLoweredToCall(const Function *F) const; + bool isLoweredToCall(const Function *F) const; + + /// Parameters that control the generic loop unrolling transformation. + struct UnrollingPreferences { + /// The cost threshold for the unrolled loop, compared to + /// CodeMetrics.NumInsts aggregated over all basic blocks in the loop body. + /// The unrolling factor is set such that the unrolled loop body does not + /// exceed this cost. Set this to UINT_MAX to disable the loop body cost + /// restriction. + unsigned Threshold; + /// If complete unrolling could help other optimizations (e.g. InstSimplify) + /// to remove N% of instructions, then we can go beyond unroll threshold. + /// This value set the minimal percent for allowing that. + unsigned MinPercentOfOptimized; + /// The absolute cost threshold. We won't go beyond this even if complete + /// unrolling could result in optimizing out 90% of instructions. + unsigned AbsoluteThreshold; + /// The cost threshold for the unrolled loop when optimizing for size (set + /// to UINT_MAX to disable). + unsigned OptSizeThreshold; + /// The cost threshold for the unrolled loop, like Threshold, but used + /// for partial/runtime unrolling (set to UINT_MAX to disable). + unsigned PartialThreshold; + /// The cost threshold for the unrolled loop when optimizing for size, like + /// OptSizeThreshold, but used for partial/runtime unrolling (set to + /// UINT_MAX to disable). + unsigned PartialOptSizeThreshold; + /// A forced unrolling factor (the number of concatenated bodies of the + /// original loop in the unrolled loop body). When set to 0, the unrolling + /// transformation will select an unrolling factor based on the current cost + /// threshold and other factors. + unsigned Count; + // Set the maximum unrolling factor. The unrolling factor may be selected + // using the appropriate cost threshold, but may not exceed this number + // (set to UINT_MAX to disable). This does not apply in cases where the + // loop is being fully unrolled. + unsigned MaxCount; + /// Allow partial unrolling (unrolling of loops to expand the size of the + /// loop body, not only to eliminate small constant-trip-count loops). + bool Partial; + /// Allow runtime unrolling (unrolling of loops to expand the size of the + /// loop body even when the number of loop iterations is not known at + /// compile time). + bool Runtime; + }; + + /// \brief Get target-customized preferences for the generic loop unrolling + /// transformation. The caller will initialize UP with the current + /// target-independent defaults. + void getUnrollingPreferences(Loop *L, UnrollingPreferences &UP) const; /// @} @@ -194,60 +279,91 @@ public: /// significantly boost the performance when the population is dense, and it /// may or may not degrade performance if the population is sparse. A HW /// support is considered as "Fast" if it can outperform, or is on a par - /// with, SW implementaion when the population is sparse; otherwise, it is + /// with, SW implementation when the population is sparse; otherwise, it is /// considered as "Slow". - enum PopcntSupportKind { - PSK_Software, - PSK_SlowHardware, - PSK_FastHardware - }; + enum PopcntSupportKind { PSK_Software, PSK_SlowHardware, PSK_FastHardware }; - /// isLegalAddImmediate - Return true if the specified immediate is legal - /// add immediate, that is the target has add instructions which can add - /// a register with the immediate without having to materialize the - /// immediate into a register. - virtual bool isLegalAddImmediate(int64_t Imm) const; + /// \brief Return true if the specified immediate is legal add immediate, that + /// is the target has add instructions which can add a register with the + /// immediate without having to materialize the immediate into a register. + bool isLegalAddImmediate(int64_t Imm) const; - /// isLegalICmpImmediate - Return true if the specified immediate is legal - /// icmp immediate, that is the target has icmp instructions which can compare - /// a register against the immediate without having to materialize the - /// immediate into a register. - virtual bool isLegalICmpImmediate(int64_t Imm) const; + /// \brief Return true if the specified immediate is legal icmp immediate, + /// that is the target has icmp instructions which can compare a register + /// against the immediate without having to materialize the immediate into a + /// register. + bool isLegalICmpImmediate(int64_t Imm) const; - /// isLegalAddressingMode - Return true if the addressing mode represented by - /// AM is legal for this target, for a load/store of the specified type. + /// \brief Return true if the addressing mode represented by AM is legal for + /// this target, for a load/store of the specified type. /// The type may be VoidTy, in which case only return true if the addressing /// mode is legal for a load/store of any legal type. /// TODO: Handle pre/postinc as well. - virtual bool isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV, - int64_t BaseOffset, bool HasBaseReg, - int64_t Scale) const; + bool isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV, int64_t BaseOffset, + bool HasBaseReg, int64_t Scale) const; + + /// \brief Return true if the target works with masked instruction + /// AVX2 allows masks for consecutive load and store for i32 and i64 elements. + /// AVX-512 architecture will also allow masks for non-consecutive memory + /// accesses. + bool isLegalMaskedStore(Type *DataType, int Consecutive) const; + bool isLegalMaskedLoad(Type *DataType, int Consecutive) const; + + /// \brief Return the cost of the scaling factor used in the addressing + /// mode represented by AM for this target, for a load/store + /// of the specified type. + /// If the AM is supported, the return value must be >= 0. + /// If the AM is not supported, it returns a negative value. + /// TODO: Handle pre/postinc as well. + int getScalingFactorCost(Type *Ty, GlobalValue *BaseGV, int64_t BaseOffset, + bool HasBaseReg, int64_t Scale) const; + + /// \brief Return true if it's free to truncate a value of type Ty1 to type + /// Ty2. e.g. On x86 it's free to truncate a i32 value in register EAX to i16 + /// by referencing its sub-register AX. + bool isTruncateFree(Type *Ty1, Type *Ty2) const; + + /// \brief Return true if it is profitable to hoist instruction in the + /// then/else to before if. + bool isProfitableToHoist(Instruction *I) const; + + /// \brief Return true if this type is legal. + bool isTypeLegal(Type *Ty) const; - /// isTruncateFree - Return true if it's free to truncate a value of - /// type Ty1 to type Ty2. e.g. On x86 it's free to truncate a i32 value in - /// register EAX to i16 by referencing its sub-register AX. - virtual bool isTruncateFree(Type *Ty1, Type *Ty2) const; + /// \brief Returns the target's jmp_buf alignment in bytes. + unsigned getJumpBufAlignment() const; - /// Is this type legal. - virtual bool isTypeLegal(Type *Ty) const; + /// \brief Returns the target's jmp_buf size in bytes. + unsigned getJumpBufSize() const; - /// getJumpBufAlignment - returns the target's jmp_buf alignment in bytes - virtual unsigned getJumpBufAlignment() const; + /// \brief Return true if switches should be turned into lookup tables for the + /// target. + bool shouldBuildLookupTables() const; - /// getJumpBufSize - returns the target's jmp_buf size in bytes. - virtual unsigned getJumpBufSize() const; + /// \brief Don't restrict interleaved unrolling to small loops. + bool enableAggressiveInterleaving(bool LoopHasReductions) const; - /// shouldBuildLookupTables - Return true if switches should be turned into - /// lookup tables for the target. - virtual bool shouldBuildLookupTables() const; + /// \brief Return hardware support for population count. + PopcntSupportKind getPopcntSupport(unsigned IntTyWidthInBit) const; - /// getPopcntSupport - Return hardware support for population count. - virtual PopcntSupportKind getPopcntSupport(unsigned IntTyWidthInBit) const; + /// \brief Return true if the hardware has a fast square-root instruction. + bool haveFastSqrt(Type *Ty) const; - /// getIntImmCost - Return the expected cost of materializing the given - /// integer immediate of the specified type. - virtual unsigned getIntImmCost(const APInt &Imm, Type *Ty) const; + /// \brief Return the expected cost of supporting the floating point operation + /// of the specified type. + unsigned getFPOpCost(Type *Ty) const; + /// \brief Return the expected cost of materializing for the given integer + /// immediate of the specified type. + unsigned getIntImmCost(const APInt &Imm, Type *Ty) const; + + /// \brief Return the expected cost of materialization for the given integer + /// immediate of the specified type for a given instruction. The cost can be + /// zero if the immediate can be folded into the specified instruction. + unsigned getIntImmCost(unsigned Opc, unsigned Idx, const APInt &Imm, + Type *Ty) const; + unsigned getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm, + Type *Ty) const; /// @} /// \name Vector Target Information @@ -257,81 +373,502 @@ public: enum ShuffleKind { SK_Broadcast, ///< Broadcast element 0 to all other elements. SK_Reverse, ///< Reverse the order of the vector. + SK_Alternate, ///< Choose alternate elements from vector. SK_InsertSubvector, ///< InsertSubvector. Index indicates start offset. SK_ExtractSubvector ///< ExtractSubvector Index indicates start offset. }; + /// \brief Additional information about an operand's possible values. + enum OperandValueKind { + OK_AnyValue, // Operand can have any value. + OK_UniformValue, // Operand is uniform (splat of a value). + OK_UniformConstantValue, // Operand is uniform constant. + OK_NonUniformConstantValue // Operand is a non uniform constant value. + }; + + /// \brief Additional properties of an operand's values. + enum OperandValueProperties { OP_None = 0, OP_PowerOf2 = 1 }; + /// \return The number of scalar or vector registers that the target has. /// If 'Vectors' is true, it returns the number of vector registers. If it is /// set to false, it returns the number of scalar registers. - virtual unsigned getNumberOfRegisters(bool Vector) const; + unsigned getNumberOfRegisters(bool Vector) const; /// \return The width of the largest scalar or vector register type. - virtual unsigned getRegisterBitWidth(bool Vector) const; + unsigned getRegisterBitWidth(bool Vector) const; - /// \return The maximum unroll factor that the vectorizer should try to + /// \return The maximum interleave factor that any transform should try to /// perform for this target. This number depends on the level of parallelism /// and the number of execution units in the CPU. - virtual unsigned getMaximumUnrollFactor() const; + unsigned getMaxInterleaveFactor() const; /// \return The expected cost of arithmetic ops, such as mul, xor, fsub, etc. - virtual unsigned getArithmeticInstrCost(unsigned Opcode, Type *Ty) const; + unsigned + getArithmeticInstrCost(unsigned Opcode, Type *Ty, + OperandValueKind Opd1Info = OK_AnyValue, + OperandValueKind Opd2Info = OK_AnyValue, + OperandValueProperties Opd1PropInfo = OP_None, + OperandValueProperties Opd2PropInfo = OP_None) const; /// \return The cost of a shuffle instruction of kind Kind and of type Tp. /// The index and subtype parameters are used by the subvector insertion and /// extraction shuffle kinds. - virtual unsigned getShuffleCost(ShuffleKind Kind, Type *Tp, int Index = 0, - Type *SubTp = 0) const; + unsigned getShuffleCost(ShuffleKind Kind, Type *Tp, int Index = 0, + Type *SubTp = nullptr) const; /// \return The expected cost of cast instructions, such as bitcast, trunc, /// zext, etc. - virtual unsigned getCastInstrCost(unsigned Opcode, Type *Dst, - Type *Src) const; + unsigned getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) const; - /// \return The expected cost of control-flow related instrutctions such as + /// \return The expected cost of control-flow related instructions such as /// Phi, Ret, Br. - virtual unsigned getCFInstrCost(unsigned Opcode) const; + unsigned getCFInstrCost(unsigned Opcode) const; /// \returns The expected cost of compare and select instructions. - virtual unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, - Type *CondTy = 0) const; + unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, + Type *CondTy = nullptr) const; /// \return The expected cost of vector Insert and Extract. /// Use -1 to indicate that there is no information on the index value. - virtual unsigned getVectorInstrCost(unsigned Opcode, Type *Val, - unsigned Index = -1) const; + unsigned getVectorInstrCost(unsigned Opcode, Type *Val, + unsigned Index = -1) const; /// \return The cost of Load and Store instructions. - virtual unsigned getMemoryOpCost(unsigned Opcode, Type *Src, - unsigned Alignment, - unsigned AddressSpace) const; + unsigned getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment, + unsigned AddressSpace) const; + + /// \return The cost of masked Load and Store instructions. + unsigned getMaskedMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment, + unsigned AddressSpace) const; + + /// \brief Calculate the cost of performing a vector reduction. + /// + /// This is the cost of reducing the vector value of type \p Ty to a scalar + /// value using the operation denoted by \p Opcode. The form of the reduction + /// can either be a pairwise reduction or a reduction that splits the vector + /// at every reduction level. + /// + /// Pairwise: + /// (v0, v1, v2, v3) + /// ((v0+v1), (v2, v3), undef, undef) + /// Split: + /// (v0, v1, v2, v3) + /// ((v0+v2), (v1+v3), undef, undef) + unsigned getReductionCost(unsigned Opcode, Type *Ty, + bool IsPairwiseForm) const; /// \returns The cost of Intrinsic instructions. - virtual unsigned getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy, - ArrayRef Tys) const; + unsigned getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy, + ArrayRef Tys) const; + + /// \returns The cost of Call instructions. + unsigned getCallInstrCost(Function *F, Type *RetTy, + ArrayRef Tys) const; /// \returns The number of pieces into which the provided type must be /// split during legalization. Zero is returned when the answer is unknown. - virtual unsigned getNumberOfParts(Type *Tp) const; + unsigned getNumberOfParts(Type *Tp) const; /// \returns The cost of the address computation. For most targets this can be /// merged into the instruction indexing mode. Some targets might want to /// distinguish between address computation for memory operations on vector /// types and scalar types. Such targets should override this function. - virtual unsigned getAddressComputationCost(Type *Ty) const; + /// The 'IsComplex' parameter is a hint that the address computation is likely + /// to involve multiple instructions and as such unlikely to be merged into + /// the address indexing mode. + unsigned getAddressComputationCost(Type *Ty, bool IsComplex = false) const; + + /// \returns The cost, if any, of keeping values of the given types alive + /// over a callsite. + /// + /// Some types may require the use of register classes that do not have + /// any callee-saved registers, so would require a spill and fill. + unsigned getCostOfKeepingLiveOverCall(ArrayRef Tys) const; + + /// \returns True if the intrinsic is a supported memory intrinsic. Info + /// will contain additional information - whether the intrinsic may write + /// or read to memory, volatility and the pointer. Info is undefined + /// if false is returned. + bool getTgtMemIntrinsic(IntrinsicInst *Inst, MemIntrinsicInfo &Info) const; + + /// \returns A value which is the result of the given memory intrinsic. New + /// instructions may be created to extract the result from the given intrinsic + /// memory operation. Returns nullptr if the target cannot create a result + /// from the given intrinsic. + Value *getOrCreateResultFromMemIntrinsic(IntrinsicInst *Inst, + Type *ExpectedType) const; /// @} - /// Analysis group identification. +private: + /// \brief The abstract base class used to type erase specific TTI + /// implementations. + class Concept; + + /// \brief The template model for the base class which wraps a concrete + /// implementation in a type erased interface. + template class Model; + + std::unique_ptr TTIImpl; +}; + +class TargetTransformInfo::Concept { +public: + virtual ~Concept() = 0; + + virtual unsigned getOperationCost(unsigned Opcode, Type *Ty, Type *OpTy) = 0; + virtual unsigned getGEPCost(const Value *Ptr, + ArrayRef Operands) = 0; + virtual unsigned getCallCost(FunctionType *FTy, int NumArgs) = 0; + virtual unsigned getCallCost(const Function *F, int NumArgs) = 0; + virtual unsigned getCallCost(const Function *F, + ArrayRef Arguments) = 0; + virtual unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy, + ArrayRef ParamTys) = 0; + virtual unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy, + ArrayRef Arguments) = 0; + virtual unsigned getUserCost(const User *U) = 0; + virtual bool hasBranchDivergence() = 0; + virtual bool isSourceOfDivergence(const Value *V) = 0; + virtual bool isLoweredToCall(const Function *F) = 0; + virtual void getUnrollingPreferences(Loop *L, UnrollingPreferences &UP) = 0; + virtual bool isLegalAddImmediate(int64_t Imm) = 0; + virtual bool isLegalICmpImmediate(int64_t Imm) = 0; + virtual bool isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV, + int64_t BaseOffset, bool HasBaseReg, + int64_t Scale) = 0; + virtual bool isLegalMaskedStore(Type *DataType, int Consecutive) = 0; + virtual bool isLegalMaskedLoad(Type *DataType, int Consecutive) = 0; + virtual int getScalingFactorCost(Type *Ty, GlobalValue *BaseGV, + int64_t BaseOffset, bool HasBaseReg, + int64_t Scale) = 0; + virtual bool isTruncateFree(Type *Ty1, Type *Ty2) = 0; + virtual bool isProfitableToHoist(Instruction *I) = 0; + virtual bool isTypeLegal(Type *Ty) = 0; + virtual unsigned getJumpBufAlignment() = 0; + virtual unsigned getJumpBufSize() = 0; + virtual bool shouldBuildLookupTables() = 0; + virtual bool enableAggressiveInterleaving(bool LoopHasReductions) = 0; + virtual PopcntSupportKind getPopcntSupport(unsigned IntTyWidthInBit) = 0; + virtual bool haveFastSqrt(Type *Ty) = 0; + virtual unsigned getFPOpCost(Type *Ty) = 0; + virtual unsigned getIntImmCost(const APInt &Imm, Type *Ty) = 0; + virtual unsigned getIntImmCost(unsigned Opc, unsigned Idx, const APInt &Imm, + Type *Ty) = 0; + virtual unsigned getIntImmCost(Intrinsic::ID IID, unsigned Idx, + const APInt &Imm, Type *Ty) = 0; + virtual unsigned getNumberOfRegisters(bool Vector) = 0; + virtual unsigned getRegisterBitWidth(bool Vector) = 0; + virtual unsigned getMaxInterleaveFactor() = 0; + virtual unsigned + getArithmeticInstrCost(unsigned Opcode, Type *Ty, OperandValueKind Opd1Info, + OperandValueKind Opd2Info, + OperandValueProperties Opd1PropInfo, + OperandValueProperties Opd2PropInfo) = 0; + virtual unsigned getShuffleCost(ShuffleKind Kind, Type *Tp, int Index, + Type *SubTp) = 0; + virtual unsigned getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) = 0; + virtual unsigned getCFInstrCost(unsigned Opcode) = 0; + virtual unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, + Type *CondTy) = 0; + virtual unsigned getVectorInstrCost(unsigned Opcode, Type *Val, + unsigned Index) = 0; + virtual unsigned getMemoryOpCost(unsigned Opcode, Type *Src, + unsigned Alignment, + unsigned AddressSpace) = 0; + virtual unsigned getMaskedMemoryOpCost(unsigned Opcode, Type *Src, + unsigned Alignment, + unsigned AddressSpace) = 0; + virtual unsigned getReductionCost(unsigned Opcode, Type *Ty, + bool IsPairwiseForm) = 0; + virtual unsigned getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy, + ArrayRef Tys) = 0; + virtual unsigned getCallInstrCost(Function *F, Type *RetTy, + ArrayRef Tys) = 0; + virtual unsigned getNumberOfParts(Type *Tp) = 0; + virtual unsigned getAddressComputationCost(Type *Ty, bool IsComplex) = 0; + virtual unsigned getCostOfKeepingLiveOverCall(ArrayRef Tys) = 0; + virtual bool getTgtMemIntrinsic(IntrinsicInst *Inst, + MemIntrinsicInfo &Info) = 0; + virtual Value *getOrCreateResultFromMemIntrinsic(IntrinsicInst *Inst, + Type *ExpectedType) = 0; +}; + +template +class TargetTransformInfo::Model final : public TargetTransformInfo::Concept { + T Impl; + +public: + Model(T Impl) : Impl(std::move(Impl)) {} + ~Model() override {} + + unsigned getOperationCost(unsigned Opcode, Type *Ty, Type *OpTy) override { + return Impl.getOperationCost(Opcode, Ty, OpTy); + } + unsigned getGEPCost(const Value *Ptr, + ArrayRef Operands) override { + return Impl.getGEPCost(Ptr, Operands); + } + unsigned getCallCost(FunctionType *FTy, int NumArgs) override { + return Impl.getCallCost(FTy, NumArgs); + } + unsigned getCallCost(const Function *F, int NumArgs) override { + return Impl.getCallCost(F, NumArgs); + } + unsigned getCallCost(const Function *F, + ArrayRef Arguments) override { + return Impl.getCallCost(F, Arguments); + } + unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy, + ArrayRef ParamTys) override { + return Impl.getIntrinsicCost(IID, RetTy, ParamTys); + } + unsigned getIntrinsicCost(Intrinsic::ID IID, Type *RetTy, + ArrayRef Arguments) override { + return Impl.getIntrinsicCost(IID, RetTy, Arguments); + } + unsigned getUserCost(const User *U) override { return Impl.getUserCost(U); } + bool hasBranchDivergence() override { return Impl.hasBranchDivergence(); } + bool isSourceOfDivergence(const Value *V) override { + return Impl.isSourceOfDivergence(V); + } + bool isLoweredToCall(const Function *F) override { + return Impl.isLoweredToCall(F); + } + void getUnrollingPreferences(Loop *L, UnrollingPreferences &UP) override { + return Impl.getUnrollingPreferences(L, UP); + } + bool isLegalAddImmediate(int64_t Imm) override { + return Impl.isLegalAddImmediate(Imm); + } + bool isLegalICmpImmediate(int64_t Imm) override { + return Impl.isLegalICmpImmediate(Imm); + } + bool isLegalAddressingMode(Type *Ty, GlobalValue *BaseGV, int64_t BaseOffset, + bool HasBaseReg, int64_t Scale) override { + return Impl.isLegalAddressingMode(Ty, BaseGV, BaseOffset, HasBaseReg, + Scale); + } + bool isLegalMaskedStore(Type *DataType, int Consecutive) override { + return Impl.isLegalMaskedStore(DataType, Consecutive); + } + bool isLegalMaskedLoad(Type *DataType, int Consecutive) override { + return Impl.isLegalMaskedLoad(DataType, Consecutive); + } + int getScalingFactorCost(Type *Ty, GlobalValue *BaseGV, int64_t BaseOffset, + bool HasBaseReg, int64_t Scale) override { + return Impl.getScalingFactorCost(Ty, BaseGV, BaseOffset, HasBaseReg, Scale); + } + bool isTruncateFree(Type *Ty1, Type *Ty2) override { + return Impl.isTruncateFree(Ty1, Ty2); + } + bool isProfitableToHoist(Instruction *I) override { + return Impl.isProfitableToHoist(I); + } + bool isTypeLegal(Type *Ty) override { return Impl.isTypeLegal(Ty); } + unsigned getJumpBufAlignment() override { return Impl.getJumpBufAlignment(); } + unsigned getJumpBufSize() override { return Impl.getJumpBufSize(); } + bool shouldBuildLookupTables() override { + return Impl.shouldBuildLookupTables(); + } + bool enableAggressiveInterleaving(bool LoopHasReductions) override { + return Impl.enableAggressiveInterleaving(LoopHasReductions); + } + PopcntSupportKind getPopcntSupport(unsigned IntTyWidthInBit) override { + return Impl.getPopcntSupport(IntTyWidthInBit); + } + bool haveFastSqrt(Type *Ty) override { return Impl.haveFastSqrt(Ty); } + + unsigned getFPOpCost(Type *Ty) override { + return Impl.getFPOpCost(Ty); + } + + unsigned getIntImmCost(const APInt &Imm, Type *Ty) override { + return Impl.getIntImmCost(Imm, Ty); + } + unsigned getIntImmCost(unsigned Opc, unsigned Idx, const APInt &Imm, + Type *Ty) override { + return Impl.getIntImmCost(Opc, Idx, Imm, Ty); + } + unsigned getIntImmCost(Intrinsic::ID IID, unsigned Idx, const APInt &Imm, + Type *Ty) override { + return Impl.getIntImmCost(IID, Idx, Imm, Ty); + } + unsigned getNumberOfRegisters(bool Vector) override { + return Impl.getNumberOfRegisters(Vector); + } + unsigned getRegisterBitWidth(bool Vector) override { + return Impl.getRegisterBitWidth(Vector); + } + unsigned getMaxInterleaveFactor() override { + return Impl.getMaxInterleaveFactor(); + } + unsigned + getArithmeticInstrCost(unsigned Opcode, Type *Ty, OperandValueKind Opd1Info, + OperandValueKind Opd2Info, + OperandValueProperties Opd1PropInfo, + OperandValueProperties Opd2PropInfo) override { + return Impl.getArithmeticInstrCost(Opcode, Ty, Opd1Info, Opd2Info, + Opd1PropInfo, Opd2PropInfo); + } + unsigned getShuffleCost(ShuffleKind Kind, Type *Tp, int Index, + Type *SubTp) override { + return Impl.getShuffleCost(Kind, Tp, Index, SubTp); + } + unsigned getCastInstrCost(unsigned Opcode, Type *Dst, Type *Src) override { + return Impl.getCastInstrCost(Opcode, Dst, Src); + } + unsigned getCFInstrCost(unsigned Opcode) override { + return Impl.getCFInstrCost(Opcode); + } + unsigned getCmpSelInstrCost(unsigned Opcode, Type *ValTy, + Type *CondTy) override { + return Impl.getCmpSelInstrCost(Opcode, ValTy, CondTy); + } + unsigned getVectorInstrCost(unsigned Opcode, Type *Val, + unsigned Index) override { + return Impl.getVectorInstrCost(Opcode, Val, Index); + } + unsigned getMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment, + unsigned AddressSpace) override { + return Impl.getMemoryOpCost(Opcode, Src, Alignment, AddressSpace); + } + unsigned getMaskedMemoryOpCost(unsigned Opcode, Type *Src, unsigned Alignment, + unsigned AddressSpace) override { + return Impl.getMaskedMemoryOpCost(Opcode, Src, Alignment, AddressSpace); + } + unsigned getReductionCost(unsigned Opcode, Type *Ty, + bool IsPairwiseForm) override { + return Impl.getReductionCost(Opcode, Ty, IsPairwiseForm); + } + unsigned getIntrinsicInstrCost(Intrinsic::ID ID, Type *RetTy, + ArrayRef Tys) override { + return Impl.getIntrinsicInstrCost(ID, RetTy, Tys); + } + unsigned getCallInstrCost(Function *F, Type *RetTy, + ArrayRef Tys) override { + return Impl.getCallInstrCost(F, RetTy, Tys); + } + unsigned getNumberOfParts(Type *Tp) override { + return Impl.getNumberOfParts(Tp); + } + unsigned getAddressComputationCost(Type *Ty, bool IsComplex) override { + return Impl.getAddressComputationCost(Ty, IsComplex); + } + unsigned getCostOfKeepingLiveOverCall(ArrayRef Tys) override { + return Impl.getCostOfKeepingLiveOverCall(Tys); + } + bool getTgtMemIntrinsic(IntrinsicInst *Inst, + MemIntrinsicInfo &Info) override { + return Impl.getTgtMemIntrinsic(Inst, Info); + } + Value *getOrCreateResultFromMemIntrinsic(IntrinsicInst *Inst, + Type *ExpectedType) override { + return Impl.getOrCreateResultFromMemIntrinsic(Inst, ExpectedType); + } +}; + +template +TargetTransformInfo::TargetTransformInfo(T Impl) + : TTIImpl(new Model(Impl)) {} + +/// \brief Analysis pass providing the \c TargetTransformInfo. +/// +/// The core idea of the TargetIRAnalysis is to expose an interface through +/// which LLVM targets can analyze and provide information about the middle +/// end's target-independent IR. This supports use cases such as target-aware +/// cost modeling of IR constructs. +/// +/// This is a function analysis because much of the cost modeling for targets +/// is done in a subtarget specific way and LLVM supports compiling different +/// functions targeting different subtargets in order to support runtime +/// dispatch according to the observed subtarget. +class TargetIRAnalysis { +public: + typedef TargetTransformInfo Result; + + /// \brief Opaque, unique identifier for this analysis pass. + static void *ID() { return (void *)&PassID; } + + /// \brief Provide access to a name for this pass for debugging purposes. + static StringRef name() { return "TargetIRAnalysis"; } + + /// \brief Default construct a target IR analysis. + /// + /// This will use the module's datalayout to construct a baseline + /// conservative TTI result. + TargetIRAnalysis(); + + /// \brief Construct an IR analysis pass around a target-provide callback. + /// + /// The callback will be called with a particular function for which the TTI + /// is needed and must return a TTI object for that function. + TargetIRAnalysis(std::function TTICallback); + + // Value semantics. We spell out the constructors for MSVC. + TargetIRAnalysis(const TargetIRAnalysis &Arg) + : TTICallback(Arg.TTICallback) {} + TargetIRAnalysis(TargetIRAnalysis &&Arg) + : TTICallback(std::move(Arg.TTICallback)) {} + TargetIRAnalysis &operator=(const TargetIRAnalysis &RHS) { + TTICallback = RHS.TTICallback; + return *this; + } + TargetIRAnalysis &operator=(TargetIRAnalysis &&RHS) { + TTICallback = std::move(RHS.TTICallback); + return *this; + } + + Result run(Function &F); + +private: + static char PassID; + + /// \brief The callback used to produce a result. + /// + /// We use a completely opaque callback so that targets can provide whatever + /// mechanism they desire for constructing the TTI for a given function. + /// + /// FIXME: Should we really use std::function? It's relatively inefficient. + /// It might be possible to arrange for even stateful callbacks to outlive + /// the analysis and thus use a function_ref which would be lighter weight. + /// This may also be less error prone as the callback is likely to reference + /// the external TargetMachine, and that reference needs to never dangle. + std::function TTICallback; + + /// \brief Helper function used as the callback in the default constructor. + static Result getDefaultTTI(Function &F); +}; + +/// \brief Wrapper pass for TargetTransformInfo. +/// +/// This pass can be constructed from a TTI object which it stores internally +/// and is queried by passes. +class TargetTransformInfoWrapperPass : public ImmutablePass { + TargetIRAnalysis TIRA; + Optional TTI; + + virtual void anchor(); + +public: static char ID; + + /// \brief We must provide a default constructor for the pass but it should + /// never be used. + /// + /// Use the constructor below or call one of the creation routines. + TargetTransformInfoWrapperPass(); + + explicit TargetTransformInfoWrapperPass(TargetIRAnalysis TIRA); + + TargetTransformInfo &getTTI(Function &F); }; -/// \brief Create the base case instance of a pass in the TTI analysis group. +/// \brief Create an analysis pass wrapper around a TTI object. /// -/// This class provides the base case for the stack of TTI analyses. It doesn't -/// delegate to anything and uses the STTI and VTTI objects passed in to -/// satisfy the queries. -ImmutablePass *createNoTargetTransformInfoPass(); +/// This analysis pass just holds the TTI instance and makes it available to +/// clients. +ImmutablePass *createTargetTransformInfoWrapperPass(TargetIRAnalysis TIRA); } // End llvm namespace